The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in this skill. The skill follows safe practices for interacting with the Harness platform using defined MCP tools.
[COMMAND_EXECUTION]: The skill uses specific tools (harness_list, harness_get) to retrieve structured data from the Harness IDP. These tools are restricted to platform-provided functionality for accessing catalog entities, scores, and technical documentation.
[PROMPT_INJECTION]: The skill contains a potential surface for indirect prompt injection by processing external data from the IDP catalog and technical documents.
Ingestion points: External data enters through the harness_list and harness_get tools used in Steps 1-5 (SKILL.md).
Boundary markers: Absent.
Capability inventory: The skill is limited to read-only tool calls for retrieving IDP scores and metadata; it lacks high-risk capabilities like file system writes or arbitrary network operations.
Sanitization: Absent.

scorecard-review